Amplitude integration is here

March 12, 2026•3 min read•Vivek Sah

Hi, this is Vivek, building Contextflo. I share practical notes on getting answers from your data, a couple of times a month.

Contextflo now connects to Amplitude. Ask about retention, funnels, user behaviour and revenue in natural language, right alongside your SQL data. One conversation, both sources, instead of switching between Amplitude dashboards and your warehouse.

What you can ask

Once connected, you can query Amplitude the way you would ask a colleague:

What does our signup-to-purchase funnel look like this month?

What's our D1, D7 and D30 retention?

Which features do our most active users use?

Look up user [email protected] and show me their recent activity

Contextflo works out which Amplitude endpoints to call, passes the right parameters, and returns a clear answer.

The endpoints it covers

The integration wraps the Amplitude Dashboard REST API:

Endpoint	What it gives you
Event Segmentation	Counts, uniques, DAU%, with grouping and filters
Funnel Analysis	Step-by-step conversion rates between events
Retention	D1/D7/D30 retention with pre-calculated percentages
Revenue LTV	ARPU, ARPPU, total revenue, paying users
User Search	Find users by email, user ID or Amplitude ID
User Activity	Full event stream for a specific user
User Composition	Breakdown by country, platform, device
User Counts	Active and new user trends over time
Event List	All tracked events with volume
Session Length	Distribution histogram of session durations
Avg Session Length	Average session duration over time
Sessions Per User	Average sessions per user over time
Real-time Active Users	Live count of currently active users
Chart Results	Pull data from saved Amplitude charts

Event List is worth knowing about even though it sounds like plumbing. Amplitude event names are whatever someone typed when they instrumented the feature, so asking for the event list first is how you find out whether the thing you care about is called checkout_completed, purchase, or Purchase Completed before you build a funnel on the wrong one.

Cross-source answers

The real gain is combining Amplitude with your SQL data in one conversation.

What's the conversion rate from signup to purchase in Amplitude, and what's the average order value for converted users in our database?

Three things happen: the Amplitude funnel API is queried for signup → purchase conversion, your warehouse is queried for average order value, and the two are combined into one answer.

Before this, that meant opening Amplitude, building a funnel chart, exporting it, switching to a SQL tool, running a query, and reconciling the two by hand. The reconciling was always the annoying part, because Amplitude counts users and your database counts orders, and deciding which one is the denominator is a judgement call somebody had to make silently every time.

Getting started

Connect Amplitude in your Contextflo settings. You will need your Amplitude API Key and Secret Key, both under your Amplitude project settings. Once connected the endpoints are immediately available in your MCP client.

Works with Claude, Cursor, and any other MCP-compatible client.

Here is a more in-depth look at Contextflo and how it works.

What is Contextflo?

Contextflo is a governed context layer between your data and the AI your team already uses. Connect your warehouse once, and your team asks questions in their own Claude or ChatGPT. The model writes and runs the SQL; Contextflo supplies the definitions, the per-user access control, and the audit that make the answers trustworthy. Your data never moves, and you do not need a data team.

How it works

Connect your data

Point Contextflo at your warehouse or database, or upload a CSV. It reaches multiple sources at once, so a single question can span all of them.

Generate context automatically

Connect your code repo, Notion docs, or a data dictionary, and Contextflo annotates each table in your data source where it can. You review and correct them. That becomes the foundational context layer: your AI agent does not just see tables, it sees the context around them.

Define metrics and save golden queries

Pin the verified SQL behind a metric once. Every question then resolves against the same definitions, so the number is consistent no matter who asks or how they phrase it.

A short walkthrough on a BigQuery warehouse.

Your team queries in their own Claude or ChatGPT over MCP, so you bring any agent rather than a locked-in bot, and every answer comes back with the SQL shown and access enforced per user.

Find out if Contextflo is the right fit for you.